{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 1000,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 5.490319312063127,
      "learning_rate": 7.692307692307694e-07,
      "logits/chosen": -1.73323655128479,
      "logits/rejected": -1.963712453842163,
      "logps/chosen": -64.71795654296875,
      "logps/rejected": -92.56527709960938,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/chosen": 0.0,
      "rewards/margins": 0.0,
      "rewards/rejected": 0.0,
      "step": 1
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.4753255673765837,
      "learning_rate": 7.692307692307694e-06,
      "logits/chosen": -1.6273242235183716,
      "logits/rejected": -1.7998943328857422,
      "logps/chosen": -78.1596450805664,
      "logps/rejected": -136.78704833984375,
      "loss": 0.5986,
      "rewards/accuracies": 0.625,
      "rewards/chosen": -0.14767809212207794,
      "rewards/margins": 0.3422772288322449,
      "rewards/rejected": -0.48995527625083923,
      "step": 10
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4922013042570934,
      "learning_rate": 9.903926402016153e-06,
      "logits/chosen": -1.132021188735962,
      "logits/rejected": -1.4362722635269165,
      "logps/chosen": -60.54664993286133,
      "logps/rejected": -335.38629150390625,
      "loss": 0.3069,
      "rewards/accuracies": 0.8812500238418579,
      "rewards/chosen": 0.005078454967588186,
      "rewards/margins": 2.449418783187866,
      "rewards/rejected": -2.444340467453003,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.08650022357203001,
      "learning_rate": 9.442228179894362e-06,
      "logits/chosen": -1.4244499206542969,
      "logits/rejected": -1.7115017175674438,
      "logps/chosen": -159.7740020751953,
      "logps/rejected": -776.4279174804688,
      "loss": 0.0327,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -0.981249213218689,
      "rewards/margins": 5.87949275970459,
      "rewards/rejected": -6.86074161529541,
      "step": 30
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.6071478933413408,
      "learning_rate": 8.633301610170136e-06,
      "logits/chosen": -1.8324272632598877,
      "logits/rejected": -2.274733781814575,
      "logps/chosen": -173.323486328125,
      "logps/rejected": -1064.7208251953125,
      "loss": 0.017,
      "rewards/accuracies": 0.9937499761581421,
      "rewards/chosen": -1.1587677001953125,
      "rewards/margins": 8.547063827514648,
      "rewards/rejected": -9.705831527709961,
      "step": 40
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.37379661402861,
      "learning_rate": 7.540376726232648e-06,
      "logits/chosen": -2.072046995162964,
      "logits/rejected": -2.5416159629821777,
      "logps/chosen": -201.16822814941406,
      "logps/rejected": -1270.976806640625,
      "loss": 0.0143,
      "rewards/accuracies": 0.987500011920929,
      "rewards/chosen": -1.3896355628967285,
      "rewards/margins": 10.439592361450195,
      "rewards/rejected": -11.829228401184082,
      "step": 50
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.08724694925694036,
      "learning_rate": 6.248882390836135e-06,
      "logits/chosen": -1.5749847888946533,
      "logits/rejected": -2.108443021774292,
      "logps/chosen": -206.0604248046875,
      "logps/rejected": -1066.5167236328125,
      "loss": 0.0116,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.477189302444458,
      "rewards/margins": 8.241119384765625,
      "rewards/rejected": -9.718308448791504,
      "step": 60
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.5412553598400243,
      "learning_rate": 4.859768718620656e-06,
      "logits/chosen": -1.5107686519622803,
      "logits/rejected": -2.1837661266326904,
      "logps/chosen": -248.97695922851562,
      "logps/rejected": -1404.155517578125,
      "loss": 0.0022,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.8567733764648438,
      "rewards/margins": 11.288753509521484,
      "rewards/rejected": -13.145527839660645,
      "step": 70
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.008991447421855448,
      "learning_rate": 3.4816162744519266e-06,
      "logits/chosen": -1.091412901878357,
      "logits/rejected": -1.767606496810913,
      "logps/chosen": -267.06280517578125,
      "logps/rejected": -1556.9952392578125,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.066657066345215,
      "rewards/margins": 12.597526550292969,
      "rewards/rejected": -14.6641845703125,
      "step": 80
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.07467711604243485,
      "learning_rate": 2.2221488349019903e-06,
      "logits/chosen": -1.1434813737869263,
      "logits/rejected": -1.8074337244033813,
      "logps/chosen": -272.1551513671875,
      "logps/rejected": -1601.199951171875,
      "loss": 0.0042,
      "rewards/accuracies": 0.9937499761581421,
      "rewards/chosen": -2.1011674404144287,
      "rewards/margins": 13.020586013793945,
      "rewards/rejected": -15.121752738952637,
      "step": 90
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.002962899425955675,
      "learning_rate": 1.1798131208919628e-06,
      "logits/chosen": -1.2595702409744263,
      "logits/rejected": -1.8675899505615234,
      "logps/chosen": -248.87960815429688,
      "logps/rejected": -1562.575927734375,
      "loss": 0.0017,
      "rewards/accuracies": 0.9937499761581421,
      "rewards/chosen": -1.868859887123108,
      "rewards/margins": 12.840827941894531,
      "rewards/rejected": -14.709688186645508,
      "step": 100
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.0049241554457892705,
      "learning_rate": 4.3608367469340553e-07,
      "logits/chosen": -1.464623212814331,
      "logits/rejected": -2.089043378829956,
      "logps/chosen": -271.04827880859375,
      "logps/rejected": -1640.91796875,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -2.086467742919922,
      "rewards/margins": 13.438623428344727,
      "rewards/rejected": -15.525090217590332,
      "step": 110
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.016229074824409925,
      "learning_rate": 4.909437331777178e-08,
      "logits/chosen": -1.3727686405181885,
      "logits/rejected": -2.019606351852417,
      "logps/chosen": -249.13632202148438,
      "logps/rejected": -1610.74951171875,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/chosen": -1.8820005655288696,
      "rewards/margins": 13.32276439666748,
      "rewards/rejected": -15.204765319824219,
      "step": 120
    },
    {
      "epoch": 5.0,
      "step": 125,
      "total_flos": 0.0,
      "train_loss": 0.07995766662200912,
      "train_runtime": 9770.964,
      "train_samples_per_second": 0.819,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 10,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}